Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =(-
    -0.07
    (artist
    -0.06
    Draft
    -0.06
     сколько
    -0.06
    	float
    -0.06
     ingr
    -0.06
     alist
    -0.06
     dsp
    -0.06
     __('
    -0.06
    	day
    -0.06
    POSITIVE LOGITS
     любой
    0.07
    坐在
    0.07
     rehearsal
    0.07
     невозможно
    0.06
     classy
    0.06
     austerity
    0.06
     输
    0.06
    _CONSTANT
    0.06
     상
    0.06
     mỹ
    0.06
    Act Density 0.002%

    No Known Activations